ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing

While forwarding we should not use the protocol path mtu to calculate
the mtu for a forwarded packet but instead use the interface mtu.

We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was
introduced for multicast forwarding. But as it does not conflict with
our usage in unicast code path it is perfect for reuse.

I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu
along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular
dependencies because of IPSKB_FORWARDED.

Because someone might have written a software which does probe
destinations manually and expects the kernel to honour those path mtus
I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone
can disable this new behaviour. We also still use mtus which are locked on a
route for forwarding.

The reason for this change is, that path mtus information can be injected
into the kernel via e.g. icmp_err protocol handler without verification
of local sockets. As such, this could cause the IPv4 forwarding path to
wrongfully emit fragmentation needed notifications or start to fragment
packets along a path.

Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED
won't be set and further fragmentation logic will use the path mtu to
determine the fragmentation size. They also recheck packet size with
help of path mtu discovery and report appropriate errors.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: John Heffner <johnwheffner@gmail.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 17 insertions, 8 deletions

diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b..e9f1217 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -54,6 +54,7 @@ static int ip_forward_finish(struct sk_buff *skb)
 
 int ip_forward(struct sk_buff *skb)
 {
+	u32 mtu;
 	struct iphdr *iph;	/* Our header */
 	struct rtable *rt;	/* Route we use */
 	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -88,11 +89,13 @@ int ip_forward(struct sk_buff *skb)
 	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
-	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
+	IPCB(skb)->flags |= IPSKB_FORWARDED;
+	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
+	if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&
 		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
 		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(dst_mtu(&rt->dst)));
+			  htonl(mtu));
 		goto drop;
 	}
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index df18461..9a78804 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -449,6 +449,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	__be16 not_last_frag;
 	struct rtable *rt = skb_rtable(skb);
 	int err = 0;
+	bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
 	dev = rt->dst.dev;
 
@@ -458,12 +459,13 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 	iph = ip_hdr(skb);
 
+	mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding);
 	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
 		     (IPCB(skb)->frag_max_size &&
-		      IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) {
+		      IPCB(skb)->frag_max_size > mtu))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
 		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
-			  htonl(ip_skb_dst_mtu(skb)));
+			  htonl(mtu));
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	}
@@ -473,7 +475,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	 */
 
 	hlen = iph->ihl * 4;
-	mtu = dst_mtu(&rt->dst) - hlen;	/* Size of data space */
+	mtu = mtu - hlen;	/* Size of data space */
 #ifdef CONFIG_BRIDGE_NETFILTER
 	if (skb->nf_bridge)
 		mtu -= nf_bridge_mtu_reduction(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f8da282..25071b4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -112,9 +112,6 @@
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
-/* IPv4 datagram length is stored into 16bit field (tot_len) */
-#define IP_MAX_MTU	0xFFFF
-
 #define RT_GC_TIMEOUT (300*HZ)
 
 static int ip_rt_max_size;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1d2480a..44eba05 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -831,6 +831,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "ip_forward_use_pmtu",
+		.data		= &init_net.ipv4.sysctl_ip_fwd_use_pmtu,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };